Picture for Chaithanya Kumar Mummadi

Chaithanya Kumar Mummadi

Text-driven Prompt Generation for Vision-Language Models in Federated Learning

Add code
Oct 09, 2023
Figure 1 for Text-driven Prompt Generation for Vision-Language Models in Federated Learning
Figure 2 for Text-driven Prompt Generation for Vision-Language Models in Federated Learning
Figure 3 for Text-driven Prompt Generation for Vision-Language Models in Federated Learning
Figure 4 for Text-driven Prompt Generation for Vision-Language Models in Federated Learning
Viaarxiv icon

AutoCLIP: Auto-tuning Zero-Shot Classifiers for Vision-Language Models

Add code
Sep 29, 2023
Viaarxiv icon

Zero-Shot Visual Classification with Guided Cropping

Add code
Sep 12, 2023
Figure 1 for Zero-Shot Visual Classification with Guided Cropping
Figure 2 for Zero-Shot Visual Classification with Guided Cropping
Figure 3 for Zero-Shot Visual Classification with Guided Cropping
Figure 4 for Zero-Shot Visual Classification with Guided Cropping
Viaarxiv icon

More Context, Less Distraction: Visual Classification by Inferring and Conditioning on Contextual Attributes

Add code
Aug 02, 2023
Figure 1 for More Context, Less Distraction: Visual Classification by Inferring and Conditioning on Contextual Attributes
Figure 2 for More Context, Less Distraction: Visual Classification by Inferring and Conditioning on Contextual Attributes
Figure 3 for More Context, Less Distraction: Visual Classification by Inferring and Conditioning on Contextual Attributes
Figure 4 for More Context, Less Distraction: Visual Classification by Inferring and Conditioning on Contextual Attributes
Viaarxiv icon

Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches

Add code
Jun 22, 2023
Figure 1 for Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches
Figure 2 for Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches
Figure 3 for Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches
Figure 4 for Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches
Viaarxiv icon

Multi-Attribute Open Set Recognition

Add code
Aug 14, 2022
Figure 1 for Multi-Attribute Open Set Recognition
Figure 2 for Multi-Attribute Open Set Recognition
Figure 3 for Multi-Attribute Open Set Recognition
Figure 4 for Multi-Attribute Open Set Recognition
Viaarxiv icon

Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain

Add code
Jul 20, 2022
Figure 1 for Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain
Figure 2 for Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain
Figure 3 for Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain
Figure 4 for Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain
Viaarxiv icon

Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness

Add code
Mar 25, 2022
Figure 1 for Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness
Figure 2 for Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness
Figure 3 for Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness
Figure 4 for Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness
Viaarxiv icon

DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunities

Add code
Aug 12, 2021
Figure 1 for DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunities
Figure 2 for DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunities
Figure 3 for DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunities
Figure 4 for DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunities
Viaarxiv icon

Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation

Add code
Jun 28, 2021
Figure 1 for Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
Figure 2 for Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
Figure 3 for Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
Figure 4 for Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
Viaarxiv icon